Related papers: BWCP: Probabilistic Learning-to-Prune Channels for…

We study network pruning which aims to remove redundant channels/kernels and hence speed up the inference of deep networks. Existing pruning methods either train from scratch with sparsity constraints or minimize the reconstruction error…

Many state-of-the-art computer vision algorithms use large scale convolutional neural networks (CNNs) as basic building blocks. These CNNs are known for their huge number of parameters, high redundancy in weights, and tremendous computing…

Despite the promising results of convolutional neural networks (CNNs), their application on devices with limited resources is still a big challenge; this is mainly due to the huge memory and computation requirements of the CNN. To counter…

Channel Pruning, widely used for accelerating Convolutional Neural Networks, is an NP-hard problem due to the inter-layer dependency of channel redundancy. Existing methods generally ignored the above dependency for computation simplicity.…

Neural network pruning techniques reduce the number of parameters without compromising predicting ability of a network. Many algorithms have been developed for pruning both over-parameterized fully-connected networks (FCNs) and…

In this paper, we propose a novel progressive parameter pruning method for Convolutional Neural Network acceleration, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic…

The success of CNNs in various applications is accompanied by a significant increase in the computation and parameter storage costs. Recent efforts toward reducing these overheads involve pruning and compressing the weights of various…

Channel-based pruning has achieved significant successes in accelerating deep convolutional neural network, whose pipeline is an iterative three-step procedure: ranking, pruning and fine-tuning. However, this iterative procedure is…

Channel pruning is widely accepted to accelerate modern convolutional neural networks (CNNs). The resulting pruned model benefits from its immediate deployment on general-purpose software and hardware resources. However, its large pruning…

Channel pruning is one of the major compression approaches for deep neural networks. While previous pruning methods have mostly focused on identifying unimportant channels, channel pruning is considered as a special case of neural…

Filter pruning method introduces structural sparsity by removing selected filters and is thus particularly effective for reducing complexity. Previous works empirically prune networks from the point of view that filter with smaller norm…

Channel pruning is a powerful technique to reduce the computational overhead of deep neural networks, enabling efficient deployment on resource-constrained devices. However, existing pruning methods often rely on local heuristics or…

Convolutional Neural Networks (CNNs) pre-trained on large-scale datasets such as ImageNet are widely used as feature extractors to construct high-accuracy classification models from scarce data for specific tasks. In such scenarios,…

As neural networks grow in size and complexity, inference speeds decline. To combat this, one of the most effective compression techniques -- channel pruning -- removes channels from weights. However, for multi-branch segments of a model,…

In recent years, deep neural networks have achieved great success in the field of computer vision. However, it is still a big challenge to deploy these deep models on resource-constrained embedded devices such as mobile robots, smart phones…

The advancement of convolutional neural networks (CNNs) on various vision applications has attracted lots of attention. Yet the majority of CNNs are unable to satisfy the strict requirement for real-world deployment. To overcome this, the…

We present a provable, sampling-based approach for generating compact Convolutional Neural Networks (CNNs) by identifying and removing redundant filters from an over-parameterized network. Our algorithm uses a small batch of input data…

Filters are the essential elements in convolutional neural networks (CNNs). Filters are corresponded to the feature maps and form the main part of the computational and memory requirement for the CNN processing. In filter pruning methods, a…

In this work, we propose a simple but effective channel pruning framework called Progressive Channel Pruning (PCP) to accelerate Convolutional Neural Networks (CNNs). In contrast to the existing channel pruning methods that prune channels…

We propose ResRep, a novel method for lossless channel pruning (a.k.a. filter pruning), which slims down a CNN by reducing the width (number of output channels) of convolutional layers. Inspired by the neurobiology research about the…